Re: [patch net-next 12/15] ipv4: fib: Notify about nexthop status changes

[Andy Gospodarek <andy@greyhouse.net>]

On Wed, Feb 08, 2017 at 11:16:39AM +0100, Jiri Pirko wrote:
> From: Ido Schimmel <idosch@mellanox.com>
> 
> When a multipath route is hit the kernel doesn't consider nexthops that
> are DEAD or LINKDOWN when IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN is set.
> Devices that offload multipath routes need to be made aware of nexthop
> status changes. Otherwise, the device will keep forwarding packets to
> non-functional nexthops.
> 
> Add the FIB_EVENT_NH_{ADD,DEL} events to the fib notification chain,
> which notify capable devices when they should add or delete a nexthop
> from their tables.

This looks good -- thanks for doing this.

IIUC the hardware forwarding use case for your hardware covered by David
Ahern's patch[1] to the ipv4 software path selection is already covered,
so this is probably the last known link/neighbor forwarding issue for
ipv4 that needs coverage.

1. a6db449 net: ipv4: Consider failed nexthops in multipath routes

> Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
> Cc: David Ahern <dsa@cumulusnetworks.com>
> Cc: Andy Gospodarek <andy@greyhouse.net>

Reviewed-by: Andy Gospodarek <gospo@broadcom.com>

> Signed-off-by: Ido Schimmel <idosch@mellanox.com>
> Signed-off-by: Jiri Pirko <jiri@mellanox.com>
> ---
>  include/net/ip_fib.h     |  7 +++++++
>  net/ipv4/fib_semantics.c | 33 +++++++++++++++++++++++++++++++++
>  2 files changed, 40 insertions(+)
> 
> diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
> index 57c2a86..45a184e 100644
> --- a/include/net/ip_fib.h
> +++ b/include/net/ip_fib.h
> @@ -214,11 +214,18 @@ struct fib_entry_notifier_info {
>  	u32 nlflags;
>  };
>  
> +struct fib_nh_notifier_info {
> +	struct fib_notifier_info info; /* must be first */
> +	struct fib_nh *fib_nh;
> +};
> +
>  enum fib_event_type {
>  	FIB_EVENT_ENTRY_ADD,
>  	FIB_EVENT_ENTRY_DEL,
>  	FIB_EVENT_RULE_ADD,
>  	FIB_EVENT_RULE_DEL,
> +	FIB_EVENT_NH_ADD,
> +	FIB_EVENT_NH_DEL,
>  };
>  
>  int register_fib_notifier(struct notifier_block *nb,
> diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
> index 6306a67..317026a 100644
> --- a/net/ipv4/fib_semantics.c
> +++ b/net/ipv4/fib_semantics.c
> @@ -1355,6 +1355,36 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local)
>  	return ret;
>  }
>  
> +static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
> +				 enum fib_event_type event_type)
> +{
> +	struct in_device *in_dev = __in_dev_get_rtnl(fib_nh->nh_dev);
> +	struct fib_nh_notifier_info info = {
> +		.fib_nh = fib_nh,
> +	};
> +
> +	switch (event_type) {
> +	case FIB_EVENT_NH_ADD:
> +		if (fib_nh->nh_flags & RTNH_F_DEAD)
> +			break;
> +		if (IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
> +		    fib_nh->nh_flags & RTNH_F_LINKDOWN)
> +			break;
> +		return call_fib_notifiers(dev_net(fib_nh->nh_dev), event_type,
> +					  &info.info);
> +	case FIB_EVENT_NH_DEL:
> +		if ((IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
> +		     fib_nh->nh_flags & RTNH_F_LINKDOWN) ||
> +		    (fib_nh->nh_flags & RTNH_F_DEAD))
> +			return call_fib_notifiers(dev_net(fib_nh->nh_dev),
> +						  event_type, &info.info);
> +	default:
> +		break;
> +	}
> +
> +	return NOTIFY_DONE;
> +}
> +
>  /* Event              force Flags           Description
>   * NETDEV_CHANGE      0     LINKDOWN        Carrier OFF, not for scope host
>   * NETDEV_DOWN        0     LINKDOWN|DEAD   Link down, not for scope host
> @@ -1396,6 +1426,8 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
>  					nexthop_nh->nh_flags |= RTNH_F_LINKDOWN;
>  					break;
>  				}
> +				call_fib_nh_notifiers(nexthop_nh,
> +						      FIB_EVENT_NH_DEL);
>  				dead++;
>  			}
>  #ifdef CONFIG_IP_ROUTE_MULTIPATH
> @@ -1550,6 +1582,7 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
>  				continue;
>  			alive++;
>  			nexthop_nh->nh_flags &= ~nh_flags;
> +			call_fib_nh_notifiers(nexthop_nh, FIB_EVENT_NH_ADD);
>  		} endfor_nexthops(fi)
>  
>  		if (alive > 0) {
> -- 
> 2.7.4
>